Browse SoTA > Computer Vision > Saliency Detection

Saliency Detection

39 papers with code · Computer Vision

Saliency Detection is a preprocessing step in computer vision which aims at finding salient objects in an image.

Source: An Unsupervised Game-Theoretic Approach to Saliency Detection

Benchmarks

Latest papers with code

Accurate RGB-D Salient Object Detection via Collaborative Learning

23 Jul 2020OIPLab-DUT/CoNet

The explicitly extracted edge information goes together with saliency to give more emphasis to the salient regions and object boundaries.

SALIENCY DETECTION SALIENT OBJECT DETECTION

2
23 Jul 2020

JIT-Masker: Efficient Online Distillation for Background Matting

11 Jun 2020josephch405/jit-masker

We design a real-time portrait matting pipeline for everyday use, particularly for "virtual backgrounds" in video conferences.

SALIENCY DETECTION

10
11 Jun 2020

Big GANs Are Watching You: Towards Unsupervised Object Segmentation with Off-the-Shelf Generative Models

8 Jun 2020anvoynov/BigGANsAreWatching

However, since generative models are known to be unstable and sensitive to hyperparameters, the training of these methods can be challenging and time-consuming.

SALIENCY DETECTION SEMANTIC SEGMENTATION UNSUPERVISED OBJECT SEGMENTATION

64
08 Jun 2020

Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection

CVPR 2020 moothes/ITSD-pytorch

Specifically, our decoder consists of two branches, a saliency branch and a contour branch.

SALIENCY DETECTION

27
01 Jun 2020

Learning Selective Self-Mutual Attention for RGB-D Saliency Detection

CVPR 2020 nnizhang/S2MA

Considering the reliability of the other modality's attention, we further propose a selection attention to weight the newly added attention term.

SALIENCY DETECTION

14
01 Jun 2020

A2dele: Adaptive and Attentive Depth Distiller for Efficient RGB-D Salient Object Detection

CVPR 2020 OIPLab-DUT/CVPR2020-A2dele

Existing state-of-the-art RGB-D salient object detection methods explore RGB-D data relying on a two-stream architecture, in which an independent subnetwork is required to process depth data.

SALIENCY DETECTION SALIENT OBJECT DETECTION

10
01 Jun 2020

Reproduction of Lateral Inhibition-Inspired Convolutional Neural Network for Visual Attention and Saliency Detection

5 May 2020fmarcinek/LICNN

I suspect that the classification of an object is strongly influenced by the background pixels on which the object is located.

SALIENCY DETECTION

1
05 May 2020

DFNet: Discriminative feature extraction and integration network for salient object detection

3 Apr 2020Sina-Mohammadi/DFNet

To address the second challenge, we propose an Attention-based Multi-level Integrator Module to give the model the ability to assign different weights to multi-level feature maps.

SALIENCY DETECTION SALIENT OBJECT DETECTION

17
03 Apr 2020

Evaluating Salient Object Detection in Natural Images with Multiple Objects having Multi-level Saliency

19 Mar 2020gokyildirim/salmon_dataset

In this paper, we corroborate based on three subjective experiments on a novel image dataset that objects in natural images are inherently perceived to have varying levels of importance.

SALIENCY DETECTION SALIENT OBJECT DETECTION

2
19 Mar 2020

Revisiting Saliency Metrics: Farthest-Neighbor Area Under Curve

CVPR 2020 SenJia/Farthest-Neighbor-AUC

Our experiment shows FN-AUC can measure spatial biases, central and peripheral, more effectively than S-AUC without penalizing the fixation locations.

QUANTIZATION SALIENCY DETECTION

1
24 Feb 2020